| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advances in Multi-Principal Element Alloys II
|
| Presentation Title |
J-23: Accelerated Development of Refractory Multi-principal Element Alloys via Machine Learning |
| Author(s) |
Carolina Frey, Anthony Botros, Chris Borg, James Saal, Bryce Meredig, Noah Phillips, Tresa Pollock |
| On-Site Speaker (Planned) |
Carolina Frey |
| Abstract Scope |
Refractory Multi-principal Element Alloys present an opportunity for new high temperature alloys that can operate at temperatures above 1200°C. However, balancing high temperature strength and room ductility remains a challenge. Machine learning methods have the potential to reduce the number of needed experiments and more efficiently discover interesting materials demonstrating necessary properties. This presentation will discuss the use of random forest machine learning algorithms in concert with CALPHAD to guide sequential alloy design. Predictive models for room temperature, 1000°C and 1200°C yield strengths are presented. High performing alloys were identified in the Hf-Mo-Nb-Ta-Ti system. Compressive mechanical properties of as-cast alloys at room and high temperature in this system are reported, and the effect of iteration on model fidelity is discussed. CALPHAD predictions are evaluated via annealing experiments at 700°C-800°C. The effect of oxygen content on strength and phase formation are also reported. Other high performing alloy systems are discussed. |
| Proceedings Inclusion? |
Planned: |